- AI
- Molecular Imaging
- CT
- X-Ray
- Ultrasound
- MRI
- Facility Management
- Mammography
False positives hamper lung CAD sensitivity
Computer-aided detection systems have proved beneficial for detecting lung nodules, but how do they fare in helping radiologists identify lung cancer? Not too well, according to a study presented at the European Congress of Radiology by a team of researchers from various institutions in South Korea.
Computer-aided detection systems have proved beneficial for detecting lung nodules, but how do they fare in helping radiologists identify lung cancer? Not too well, according to a study presented at the European Congress of Radiology by a team of researchers from various institutions in South Korea.
Led by Dr. Jin Mo Goo, investigators evaluated 150 chest CT exams that included 23 lung cancers less than 20 mm in size as well as normal cases.
Five chest radiologists and five radiology residents independently recorded the locus of each nodule candidate and assigned confidence scores to each based on likelihood of nodule and malignancy without CAD. They then repeated analysis with CAD.
Lung nodule detection significantly increased with CAD for all radiologists and subgroups of chest radiologists and radiology residents. CAD itself detected 18 of 23 lung cancers. Four lung cancers missed by three radiology residents on initial reading were additionally detected with CAD.
However, because the number of false-positive detections for lung cancer increased with the use of CAD, the overall performance of lung cancer detection was not significantly different with and without CAD for all radiologists and subgroups, according to Goo.
Four Strategies to Address the Tipping Point in Radiology
January 17th 2025In order to flip the script on the impact of the radiology workforce shortage, radiology groups and practices need to make sound investments in technologies and leverage partnerships to mitigate gaps in coverage and maximize workflow efficiencies.
Can Generative AI Facilitate Simulated Contrast Enhancement for Prostate MRI?
January 14th 2025Deep learning synthesis of contrast-enhanced MRI from non-contrast prostate MRI sequences provided an average multiscale structural similarity index of 70 percent with actual contrast-enhanced prostate MRI in external validation testing from newly published research.
Can MRI-Based AI Enhance Risk Stratification in Prostate Cancer?
January 13th 2025Employing baseline MRI and clinical data, an emerging deep learning model was 32 percent more likely to predict the progression of low-risk prostate cancer (PCa) to clinically significant prostate cancer (csPCa), according to new research.
